Artificial intelligence in predicting early-onset adjacent segment degeneration following anterior cervical discectomy and fusion
Purpose Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF. Methods Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance. Results In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features. Conclusions Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care..
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:31 |
---|---|
Enthalten in: |
European spine journal - 31(2022), 8 vom: 11. Mai, Seite 2104-2114 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Rudisill, Samuel S. [VerfasserIn] |
---|
Links: |
Volltext [lizenzpflichtig] |
---|
Themen: |
Adjacent segment |
---|
Anmerkungen: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
---|
doi: |
10.1007/s00586-022-07238-3 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
SPR047727896 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | SPR047727896 | ||
003 | DE-627 | ||
005 | 20230519232349.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220731s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s00586-022-07238-3 |2 doi | |
035 | |a (DE-627)SPR047727896 | ||
035 | |a (SPR)s00586-022-07238-3-e | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Rudisill, Samuel S. |e verfasserin |0 (orcid)0000-0003-1325-4395 |4 aut | |
245 | 1 | 0 | |a Artificial intelligence in predicting early-onset adjacent segment degeneration following anterior cervical discectomy and fusion |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 | ||
520 | |a Purpose Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF. Methods Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance. Results In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features. Conclusions Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care. | ||
650 | 4 | |a Artificial intelligence |7 (dpeaa)DE-He213 | |
650 | 4 | |a Machine learning |7 (dpeaa)DE-He213 | |
650 | 4 | |a Predictive modeling |7 (dpeaa)DE-He213 | |
650 | 4 | |a Anterior cervical discectomy |7 (dpeaa)DE-He213 | |
650 | 4 | |a Fusion |7 (dpeaa)DE-He213 | |
650 | 4 | |a Cervical spine |7 (dpeaa)DE-He213 | |
650 | 4 | |a Adjacent segment |7 (dpeaa)DE-He213 | |
650 | 4 | |a Disc |7 (dpeaa)DE-He213 | |
650 | 4 | |a Degeneration |7 (dpeaa)DE-He213 | |
650 | 4 | |a Outcomes |7 (dpeaa)DE-He213 | |
700 | 1 | |a Hornung, Alexander L. |4 aut | |
700 | 1 | |a Barajas, J. Nicolás |4 aut | |
700 | 1 | |a Bridge, Jack J. |4 aut | |
700 | 1 | |a Mallow, G. Michael |4 aut | |
700 | 1 | |a Lopez, Wylie |4 aut | |
700 | 1 | |a Sayari, Arash J. |4 aut | |
700 | 1 | |a Louie, Philip K. |4 aut | |
700 | 1 | |a Harada, Garrett K. |4 aut | |
700 | 1 | |a Tao, Youping |4 aut | |
700 | 1 | |a Wilke, Hans-Joachim |4 aut | |
700 | 1 | |a Colman, Matthew W. |4 aut | |
700 | 1 | |a Phillips, Frank M. |4 aut | |
700 | 1 | |a An, Howard S. |4 aut | |
700 | 1 | |a Samartzis, Dino |4 aut | |
773 | 0 | 8 | |i Enthalten in |t European spine journal |d Berlin : Springer, 1992 |g 31(2022), 8 vom: 11. Mai, Seite 2104-2114 |w (DE-627)SPR006873383 |w (DE-600)1472721-3 |x 1432-0932 |7 nnns |
773 | 1 | 8 | |g volume:31 |g year:2022 |g number:8 |g day:11 |g month:05 |g pages:2104-2114 |
856 | 4 | 0 | |u https://dx.doi.org/10.1007/s00586-022-07238-3 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_SPRINGER | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |d 31 |j 2022 |e 8 |b 11 |c 05 |h 2104-2114 |